… of reinforcement learning (RL). It may also lead to fairer algorithms, since a diverse ensemble
may learn … For reinforcement learning specifically, we believe our behavioral embeddings …

… We showed experimentally the effectiveness of the resulting QD-RL framework, which can
solve in two days with 20 CPUs problems which were previously out of reach without a much …

… Maximize Ensemble Diversity in Reinforcement Learning (… diversity in the ensemblebased
deep reinforcement learning … learning has been used to perform effective exploration and …

… To validate the effectiveness of the proposed diversity-driven … challenges, and learn effective
policies even when the reward … to demonstrate the benefits of diversity-driven exploration …

… Promoting diversity of strategies is also an effective method for solving games with non-transitive
dynamics [1, 40, 12, 46]. In general, an arbitrary game, of either the normal-form type [5] …

… generalization and diversity in the multi-… diversity. Results demonstrate that population size
and intrinsic motivation are both effective methods of generating greater population diversity. …

… In D2RL, the Determinantal Point Process (DPP) is used to generate diverse, while relevant
… an actor-critic reinforcement learning framework. To demonstrate the effectiveness of the …

… Khadka and Tumer [20] proposed evolutionary reinforcement learning (ERL) by effectively
combining the evolutionary algorithm based on population with DDPG. Based on ERL, …

… We find it effective to provide statistics from the beginning of a game to the current state (the
number of frames, the number of fire, left, right, up, down actions and the number of action …

… Reinforcement Learning (RL) is an effective method for training agents to make decisions
in a given environment, which is often to obtain a policy maximizing the expected cumulative …